Transformers

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 1196048
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2024-09-03T15:32:08.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 1194611,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 1198266,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 1.1946111917495728,
          "ms_50": 1.1960480213165283,
          "ms_80": 1.1982656717300415
        },
        "benchmark": "embedding/full",
        "externalId": "embedding/full/huggingface/nvidia-a100-sxm4-80gb/batch32-hidden768-seq512-vocab65536-fp32/2024-09-03-15-32-08"
      },
      "protocolDigest": "sha256:5b02ee9a2140fbc6fcc1c89800f6c177ba22718c8897cb532bf0ba91867c1e58",
      "workloadDigest": "sha256:1bf32db8b9c8b199b86f23aa3d5ef8a6d8143f2c53e6b0ef91aea81e141df414",
      "environmentDigest": "sha256:90c9e2764222f592477cfccf3373519add5a1b881563956ad058c4f99e41b6b9",
      "implementationDigest": "sha256:d6d77034622d5e42573eea7b71fb3324fcf78d3b87c20c053defd81748caefe8"
    },
    "metadata": {
      "name": "liger-embedding-full-huggingface-nvidia-a100-sxm4-80gb-batch32-hidden768-seq512-vocab65536-fp32-2024",
      "title": "Embedding lookup · huggingface · full",
      "labels": {
        "liger_version": "0.2.1"
      }
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  },
  "protocol": {
    "kind": "BenchmarkProtocol",
    "spec": {
      "harness": {
        "name": "Liger-Kernel benchmark scripts",
        "repository": "https://github.com/linkedin/Liger-Kernel"
      },
      "measurement": {
        "timer": "cuda_events",
        "primaryStatistic": "median"
      },
      "comparability": {
        "notes": "Timed: the forward pass plus the backward pass, via triton.testing.do_bench with quantiles 0.5/0.2/0.8 (median with p20/p80 spread). The upstream CSV records no CUDA, driver, or torch version; the Liger release rides each run's labels. Comparable only within one kernel, workload, timed pass, and GPU.",
        "family": "liger_kernel_bench"
      }
    },
    "metadata": {
      "name": "liger-bench-do-bench-full",
      "title": "Liger benchmark harness · full pass"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  },
  "environment": {
    "kind": "ExecutionEnvironment",
    "spec": {
      "hardware": {
        "vendor": "nvidia",
        "product": "NVIDIA A100",
        "formFactor": "SXM4-80GB",
        "architecture": "sm_80"
      },
      "software": {}
    },
    "metadata": {
      "name": "liger-bench-nvidia-a100-sxm4-80gb",
      "title": "Liger benchmark host · A100-SXM4-80GB"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}